Pith. sign in

REVIEW 1 cited by

Depth with Nonlinearity Creates No Bad Local Minima in ResNets

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1810.09038 v3 pith:WPVNMEFT submitted 2018-10-21 stat.ML cs.AIcs.LGmath.OC

classification stat.MLcs.AIcs.LGmath.OC
keywords localminimaresnetscreatesdeepdepthnonlinearityactivation
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this paper, we prove that depth with nonlinearity creates no bad local minima in a type of arbitrarily deep ResNets with arbitrary nonlinear activation functions, in the sense that the values of all local minima are no worse than the global minimum value of corresponding classical machine-learning models, and are guaranteed to further improve via residual representations. As a result, this paper provides an affirmative answer to an open question stated in a paper in the conference on Neural Information Processing Systems 2018. This paper advances the optimization theory of deep learning only for ResNets and not for other network architectures.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes

    stat.ML 2019-08 conditional novelty 6.0 of 10

    Gradient descent on a network with a final hidden layer of width O(n) can interpolate any n-point dataset and reach a global optimum, and this linear rate is optimal.

Pith tools